【摘要】：選取與認(rèn)知表現(xiàn)分?jǐn)?shù)相關(guān)性高的結(jié)構(gòu)網(wǎng)絡(luò)拓?fù)涮卣?利用這些特征建立分類模型,實(shí)現(xiàn)對(duì)正常老化者及遺忘型輕度認(rèn)知障礙(aMCI)患者的分類。本研究包含兩組擴(kuò)散張量影像(DTI)數(shù)據(jù),一組為52例正常老化受試者,一組為39例aMCI患者。分別對(duì)兩組數(shù)據(jù)進(jìn)行結(jié)構(gòu)網(wǎng)絡(luò)構(gòu)建,采用圖論分析法提取結(jié)構(gòu)網(wǎng)絡(luò)的特征,將所有特征與簡單智能狀態(tài)檢查量表(MMSE)分?jǐn)?shù)進(jìn)行相關(guān)性分析,選取與認(rèn)知表現(xiàn)分?jǐn)?shù)高度相關(guān)的特征,基于這些特征建立5種分類模型,并對(duì)模型的分類效果進(jìn)行評(píng)估。對(duì)于正常老化數(shù)據(jù),選出18個(gè)與認(rèn)知能力顯著相關(guān)的結(jié)構(gòu)網(wǎng)絡(luò)特征,集中于解剖自動(dòng)貼標(biāo)(AAL)圖譜中的9個(gè)腦區(qū);對(duì)于aMCI數(shù)據(jù),也選出18個(gè)與認(rèn)知能力顯著相關(guān)的結(jié)構(gòu)網(wǎng)絡(luò)特征,集中于AAL圖譜中的9個(gè)腦區(qū);二者選出的特征及分布的腦區(qū)是不同的。通過對(duì)分類模型的評(píng)估,得出支持向量機(jī)序列最小優(yōu)化算法建立的模型分類效果最佳,特異性達(dá)到88.46%,敏感性達(dá)到83.05%,準(zhǔn)確性達(dá)到85.71%。所提取的與認(rèn)知表現(xiàn)相關(guān)性高的結(jié)構(gòu)網(wǎng)絡(luò)特征,可以作為生物標(biāo)記指針,來建立分類模型,對(duì)正常老化者及aMCI患者進(jìn)行分類,也可提供相應(yīng)腦區(qū)間連接變化的信息。
[Abstract]:The structural network topological features with high correlation with cognitive performance scores were selected and used to establish classification models to classify (aMCI) patients with normal aging and amnesia mild cognitive impairment. This study included two groups of diffusion tensor imaging (DTI) data, one group of 52 normal aging subjects and the other group of 39 patients with aMCI. The structural network of the two groups of data is constructed respectively. The features of the structural network are extracted by graph theory analysis. The correlation between all the features and the (MMSE) score of the simple Intelligent State examination scale is analyzed. The features highly related to the cognitive performance score are selected. Based on these features, five classification models are established, and the classification effect of the model is evaluated. For the normal aging data, 18 structural network features significantly related to cognitive ability were selected, focusing on 9 brain regions in the anatomical automatic labeling (AAL) map, and for aMCI data, 18 structural network features significantly related to cognitive ability were also selected, concentrated in 9 brain regions in the AAL map, and the selected characteristics and distributed brain regions were different. Through the evaluation of the classification model, it is concluded that the model established by the support vector machine sequence minimum optimization algorithm has the best classification effect, the specificity is 88.46%, the sensitivity is 83.05%, and the accuracy is 85.71%. The extracted structural network features, which are highly correlated with cognitive performance, can be used as biomarkers to establish classification models to classify normal aging patients and aMCI patients, and can also provide information on the changes of connections between brain regions.
【作者單位】： 北京工業(yè)大學(xué)生命科學(xué)與生物工程學(xué)院;長庚大學(xué)資訊工程學(xué)系;長庚大學(xué)健康老化中心;陽明大學(xué)生物醫(yī)學(xué)影像暨放射科學(xué)系;陽明大學(xué)醫(yī)學(xué)系;
【基金】：長庚大學(xué)研究計(jì)劃(UERPD2B0301,UERPD2C0041) 長庚大學(xué)健康老化中心計(jì)劃(CMRPD1B0331,EMRPD1D0261)
【分類號(hào)】：R749.1

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 賈建平;重視輕度認(rèn)知障礙與老年性癡呆關(guān)系的研究[J];中華神經(jīng)科雜志;2002年06期

2 黃覺斌,張振馨;輕度認(rèn)知障礙的現(xiàn)代概念和研究進(jìn)展[J];中華神經(jīng)科雜志;2002年06期

3 白靜,王蔭華,翁旭初,謝晟;輕度認(rèn)知障礙患者計(jì)算能力的fMRI研究[J];中國康復(fù)理論與實(shí)踐;2003年05期

4 周衛(wèi)東,賈建平;血漿血紅素加氧酶1測定在輕度認(rèn)知障礙和老年性癡呆中的臨床意義[J];中國神經(jīng)精神疾病雜志;2004年04期

5 熊光潤,陳靜,王虹敏,顧昱,熊芳琴,馮玲,譚曉敏,王靜;輕度認(rèn)知障礙患者情感圖片再認(rèn)的研究[J];神經(jīng)疾病與精神衛(wèi)生;2004年03期

6 周愛紅,王蔭華,周曉林;輕度阿爾茨海默病患者和輕度認(rèn)知功能障礙患者注意功能的研究(英文)[J];中國臨床康復(fù);2005年05期

7 李剛;;老年認(rèn)知障礙的流行性與嚴(yán)重性[J];國外醫(yī)學(xué).老年醫(yī)學(xué)分冊;1998年04期

8 王利平;王鑫;南光賢;;腦梗死后血管性認(rèn)知障礙的臨床觀察[J];中國實(shí)驗(yàn)診斷學(xué);2008年05期

9 馬立華;;輕度認(rèn)知障礙研究現(xiàn)狀[J];中國醫(yī)學(xué)文摘.內(nèi)科學(xué);2004年01期

10 劉建輝;冀鳳云;;血管性認(rèn)知障礙與輕度認(rèn)知障礙的研究進(jìn)展[J];中國腦血管病雜志;2007年05期

相關(guān)會(huì)議論文 前10條

1 陳健華;唐牟尼;;廣州市城鄉(xiāng)養(yǎng)老院60歲以上人群,輕度認(rèn)知障礙和癡呆患者死亡率和生存率的研究[A];中華醫(yī)學(xué)會(huì)精神病學(xué)分會(huì)第九次全國學(xué)術(shù)會(huì)議論文集[C];2011年

2 岳春賢;張志s，

本文編號(hào)：2501544